agentleFS
Sign inStart free
ForgeyClapForgeyClap/Forge-Core/.claude/skills/forge-website/SKILL.md

forge-website

Skill2 starsChanged 7 days agoMITView on GitHub

Playbook for websites, landing pages and frontend UI: responsive, SEO (gebruik bij een website).

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use for: websites, landing pages and frontend UI: responsive, SEO, accessibility.

    line 11
  2. Very specific:

    No placeholder/Lorem/test/mock content in anything headed for prod.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Forge playbook — Website / landing / frontend

When to use

  • Use for: websites, landing pages and frontend UI: responsive, SEO, accessibility.

Do not duplicate ECC skills — defer to: design-is (design audit), browser (screenshot loop). This file is orchestration only.

Hard rules

  • Mobile and desktop layout verified by screenshot before claiming done.
  • No placeholder/Lorem/test/mock content in anything headed for prod.
  • Forms validate input and hit a real endpoint; clear error + success states.
  • Any analytics/form keys live in env, never in the committed bundle.
  • Meta and sharing basics: every page has a unique title and meta description, a canonical URL, Open Graph title/description/image, and JSON-LD (Organization or WebSite) where it fits — checked in the built HTML.
  • Performance proof: run Lighthouse or PageSpeed on the built site and report LCP, CLS and INP; numbers measured on localhost are labelled "local, indicative".
  • Design before markup: write the token plan from forge-craft.cjs lens --type web-ui (guidance: colours, type roles, spacing, layout sketch) and hold it against the brief; the brief's own visual direction always wins.
  • Finish gate: a page is done only when craft-evidence-web-ui.json (a screenshot per viewport and per state, or n/a with a reason) passes node .claude/forge-bin/forge-craft-evidence.cjs check --run <run_id> --type web-ui (exit 0).

Team (conditional by stack/level)

  • Lead: planner / architect.
  • Build review: react-reviewer or vue-reviewer (by stack).
  • Audits (parallel): a11y-architect, seo-specialist, performance-optimizer.
  • Copy/CTA: marketing-agent.

Skills / commands / MCP

Skills, commands, MCP and opt-in dependencies: references/team-and-tools.md.

Fan-out & flow

L2 for a single page, L3 for a multi-page site. Serial: design direction (design-is) → build → audits → fixes → review gate. Parallel: a11y ∥ seo ∥ performance ∥ copy audits on the built artifact (independent).

Domain gates

Accessibility pass; SEO meta/OG + canonical; performance budget (see ~/.claude/rules/ecc/web/performance.md); responsive at ~360/768/1280; CTA clarity; no broken links.

Ship-readiness (unique)

Screenshots at mobile+desktop breakpoints; no test copy; all CTAs/links resolve; forms submit to a real endpoint with validation; favicon/meta/OG present; 404 route; secrets in env. The ship-readiness website checklist is advisory; optionally run codex-reviewer (Codex) on important code — not a blocker.

Safety, approval and honesty

  • Approval / safety: analytics/form keys in env, never in the committed bundle.
  • Honest failure: mobile and desktop verified by screenshot before claiming done; localhost performance numbers are labelled "local, indicative".
  • Shared gates for every playbook (honesty, owner approval, secrets, reviews): .claude/docs/forge-reference/playbook-template.md.

References

  • references/team-and-tools.md — full team roster, skills, commands, MCP and opt-in runtimes.
  • references/react-best-practices.md — React / Next.js rules by impact plus the interface review list (a11y, forms, motion, state, copy); measured speed and SEO work goes to forge-web-quality.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free